Online Multiclass Boosting
Machine Learning
2018-02-27 v3 Machine Learning
Abstract
Recent work has extended the theoretical analysis of boosting algorithms to multiclass problems and to online settings. However, the multiclass extension is in the batch setting and the online extensions only consider binary classification. We fill this gap in the literature by defining, and justifying, a weak learning condition for online multiclass boosting. This condition leads to an optimal boosting algorithm that requires the minimal number of weak learners to achieve a certain accuracy. Additionally, we propose an adaptive algorithm which is near optimal and enjoys an excellent performance on real data due to its adaptive property.
Cite
@article{arxiv.1702.07305,
title = {Online Multiclass Boosting},
author = {Young Hun Jung and Jack Goetz and Ambuj Tewari},
journal= {arXiv preprint arXiv:1702.07305},
year = {2018}
}
Comments
28 pages, 2 figures